andreas128 / Srflow
Licence: other
Official SRFlow training code: Super-Resolution using Normalizing Flow in PyTorch
Stars: ✭ 537
Projects that are alternatives of or similar to Srflow
Highres Net
Pytorch implementation of HighRes-net, a neural network for multi-frame super-resolution, trained and tested on the European Space Agency’s Kelvin competition.
Stars: ✭ 207 (-61.45%)
Mutual labels: jupyter-notebook, super-resolution
Enet Real Time Semantic Segmentation
ENet - A Neural Net Architecture for real time Semantic Segmentation
Stars: ✭ 238 (-55.68%)
Mutual labels: jupyter-notebook, paper
Research Paper Notes
Notes and Summaries on ML-related Research Papers (with optional implementations)
Stars: ✭ 218 (-59.4%)
Mutual labels: jupyter-notebook, paper
Super resolution with cnns and gans
Image Super-Resolution Using SRCNN, DRRN, SRGAN, CGAN in Pytorch
Stars: ✭ 176 (-67.23%)
Mutual labels: jupyter-notebook, super-resolution
Faceswap Gan
A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.
Stars: ✭ 3,099 (+477.09%)
Mutual labels: jupyter-notebook, image-manipulation
Dragan
A stable algorithm for GAN training
Stars: ✭ 189 (-64.8%)
Mutual labels: jupyter-notebook, paper
Zoom Learn Zoom
computational zoom from raw sensor data
Stars: ✭ 224 (-58.29%)
Mutual labels: jupyter-notebook, super-resolution
Reproduce Stock Market Direction Random Forests
Reproduce research from paper "Predicting the direction of stock market prices using random forest"
Stars: ✭ 67 (-87.52%)
Mutual labels: jupyter-notebook, paper
Awesome-ICCV2021-Low-Level-Vision
A Collection of Papers and Codes for ICCV2021 Low Level Vision and Image Generation
Stars: ✭ 163 (-69.65%)
Mutual labels: image-manipulation, super-resolution
TMNet
The official pytorch implemention of the CVPR paper "Temporal Modulation Network for Controllable Space-Time Video Super-Resolution".
Stars: ✭ 77 (-85.66%)
Mutual labels: paper, super-resolution
Action Recognition Visual Attention
Action recognition using soft attention based deep recurrent neural networks
Stars: ✭ 350 (-34.82%)
Mutual labels: jupyter-notebook, paper
Cvpr 2019 Paper Statistics
Statistics and Visualization of acceptance rate, main keyword of CVPR 2019 accepted papers for the main Computer Vision conference (CVPR)
Stars: ✭ 527 (-1.86%)
Mutual labels: jupyter-notebook, paper
Nlp Tutorial
Natural Language Processing Tutorial for Deep Learning Researchers
Stars: ✭ 9,895 (+1742.64%)
Mutual labels: jupyter-notebook, paper
Triplet Attention
Official PyTorch Implementation for "Rotate to Attend: Convolutional Triplet Attention Module." [WACV 2021]
Stars: ✭ 222 (-58.66%)
Mutual labels: jupyter-notebook, paper
Deep Embedded Memory Networks
https://arxiv.org/abs/1707.00836
Stars: ✭ 19 (-96.46%)
Mutual labels: jupyter-notebook, paper
Super Resolution
Tensorflow 2.x based implementation of EDSR, WDSR and SRGAN for single image super-resolution
Stars: ✭ 952 (+77.28%)
Mutual labels: jupyter-notebook, super-resolution
libpillowfight
Small library containing various image processing algorithms (+ Python 3 bindings) that has almost no dependencies -- Moved to Gnome's Gitlab
Stars: ✭ 60 (-88.83%)
Mutual labels: paper, image-manipulation
Pytorch Vdsr
VDSR (CVPR2016) pytorch implementation
Stars: ✭ 313 (-41.71%)
Mutual labels: jupyter-notebook, super-resolution
SRFlow
[Paper] ECCV 2020 Spotlight
Setup: Data, Environment, PyTorch Demo
git clone https://github.com/andreas128/SRFlow.git && cd SRFlow && ./setup.sh
This oneliner will:
- Clone SRFlow
- Setup a python3 virtual env
- Install the packages from
requirements.txt
- Download the pretrained models
- Download the validation data
- Run the Demo Jupyter Notebook
If you want to install it manually, read the setup.sh
file. (Links to data/models, pip packages)
Demo: Try Normalizing Flow in PyTorch
./run_jupyter.sh
This notebook lets you:
- Load the pretrained models.
- Super-resolve images.
- Measure PSNR/SSIM/LPIPS.
- Infer the Normalizing Flow latent space.
Testing: Apply the included pretrained models
source myenv/bin/activate # Use the env you created using setup.sh
cd code
CUDA_VISIBLE_DEVICES=-1 python test.py ./confs/SRFlow_DF2K_4X.yml # Diverse Images 4X (Dataset Included)
CUDA_VISIBLE_DEVICES=-1 python test.py ./confs/SRFlow_DF2K_8X.yml # Diverse Images 8X (Dataset Included)
CUDA_VISIBLE_DEVICES=-1 python test.py ./confs/SRFlow_CelebA_8X.yml # Faces 8X
For testing, we apply SRFlow to the full images on CPU.
Training: Reproduce or train on your Data
The following commands train the Super-Resolution network using Normalizing Flow in PyTorch:
source myenv/bin/activate # Use the env you created using setup.sh
cd code
python train.py -opt ./confs/SRFlow_DF2K_4X.yml # Diverse Images 4X (Dataset Included)
python train.py -opt ./confs/SRFlow_DF2K_8X.yml # Diverse Images 8X (Dataset Included)
python train.py -opt ./confs/SRFlow_CelebA_8X.yml # Faces 8X
- To reduce the GPU memory, reduce the batch size in the yml file.
- CelebA does not allow us to host the dataset. A script will follow.
Dataset: How to train on your own data
The following command creates the pickel files that you can use in the yaml config file:
cd code
python prepare_data.py /path/to/img_dir
The precomputed DF2K dataset gets downloaded using setup.sh
. You can reproduce it or prepare your own dataset.
Our paper explains
-
How to train Conditional Normalizing Flow
We designed an architecture that archives state-of-the-art super-resolution quality. -
How to train Normalizing Flow on a single GPU
We based our network on GLOW, which uses up to 40 GPUs to train for image generation. SRFlow only needs a single GPU for training conditional image generation. -
How to use Normalizing Flow for image manipulation
How to exploit the latent space for Normalizing Flow for controlled image manipulations -
See many Visual Results
Compare GAN vs Normalizing Flow yourself. We've included a lot of visuals results in our [Paper].
GAN vs Normalizing Flow - Blog
- Sampling: SRFlow outputs many different images for a single input.
- Stable Training: SRFlow has much fewer hyperparameters than GAN approaches, and we did not encounter training stability issues.
- Convergence: While GANs cannot converge, conditional Normalizing Flows converge monotonic and stable.
- Higher Consistency: When downsampling the super-resolution, one obtains almost the exact input.
Get a quick introduction to Normalizing Flow in our [Blog].
Wanna help to improve the code?
If you found a bug or improved the code, please do the following:
- Fork this repo.
- Push the changes to your repo.
- Create a pull request.
Paper
@inproceedings{lugmayr2020srflow,
title={SRFlow: Learning the Super-Resolution Space with Normalizing Flow},
author={Lugmayr, Andreas and Danelljan, Martin and Van Gool, Luc and Timofte, Radu},
booktitle={ECCV},
year={2020}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].